© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 223571
    Prev
    Next
    INDEX
    Explanations

    legal/technical terms

    np_acts-logits-general · gemini-2.5-flash-lite

    generally stable, recommended

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    关于
    0.51
    ري
    0.47
    ‌
    0.46
    4
    0.45
    6
    0.45
     I
    0.45
    1
    0.45
    द्दा
    0.44
    !
    0.44
     kit
    0.43
    POSITIVE LOGITS
     различ
    0.53
    秞
    0.50
     እድ
    0.49
    leased
    0.48
     миру
    0.48
     кило
    0.47
     लौटा
    0.47
     Apica
    0.47
     ಹೋಗ
    0.47
    ༌
    0.46
    Activations Density 0.000%

    No Known Activations